1daniar's picture
First Push
2679567
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9465897679328918,
"min": 0.9465897679328918,
"max": 2.873558521270752,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9038.0390625,
"min": 9038.0390625,
"max": 29428.11328125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.039485931396484,
"min": 0.34774354100227356,
"max": 13.039485931396484,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2542.69970703125,
"min": 67.46224975585938,
"max": 2656.5966796875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06499967978343907,
"min": 0.062386852443844815,
"max": 0.07518629161909214,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2599987191337563,
"min": 0.24954740977537926,
"max": 0.35866556118593973,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1985896581089964,
"min": 0.0912739220577493,
"max": 0.29281870933140025,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7943586324359856,
"min": 0.3650956882309972,
"max": 1.4640935466570013,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.84090909090909,
"min": 2.6363636363636362,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 116.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 2.6363636363636362,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 116.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1690354097",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1690354585"
},
"total": 487.999028673,
"count": 1,
"self": 0.38410126499996977,
"children": {
"run_training.setup": {
"total": 0.034257854000031784,
"count": 1,
"self": 0.034257854000031784
},
"TrainerController.start_learning": {
"total": 487.580669554,
"count": 1,
"self": 0.5775886970018291,
"children": {
"TrainerController._reset_env": {
"total": 5.047863359000019,
"count": 1,
"self": 5.047863359000019
},
"TrainerController.advance": {
"total": 481.79509059399817,
"count": 18200,
"self": 0.2809793420026381,
"children": {
"env_step": {
"total": 481.51411125199553,
"count": 18200,
"self": 348.99749993299923,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.22341328898938,
"count": 18200,
"self": 1.8292233329870555,
"children": {
"TorchPolicy.evaluate": {
"total": 130.39418995600232,
"count": 18200,
"self": 130.39418995600232
}
}
},
"workers": {
"total": 0.2931980300069199,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 485.8170922800066,
"count": 18200,
"is_parallel": true,
"self": 228.22176453401335,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00721592000002147,
"count": 1,
"is_parallel": true,
"self": 0.004385154999908991,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028307650001124784,
"count": 10,
"is_parallel": true,
"self": 0.0028307650001124784
}
}
},
"UnityEnvironment.step": {
"total": 0.03715367699999206,
"count": 1,
"is_parallel": true,
"self": 0.00046956900001760005,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003434380000157944,
"count": 1,
"is_parallel": true,
"self": 0.0003434380000157944
},
"communicator.exchange": {
"total": 0.03424489799999719,
"count": 1,
"is_parallel": true,
"self": 0.03424489799999719
},
"steps_from_proto": {
"total": 0.002095771999961471,
"count": 1,
"is_parallel": true,
"self": 0.0005181319999110201,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001577640000050451,
"count": 10,
"is_parallel": true,
"self": 0.001577640000050451
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 257.59532774599325,
"count": 18199,
"is_parallel": true,
"self": 10.764359963990103,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.61647476299629,
"count": 18199,
"is_parallel": true,
"self": 5.61647476299629
},
"communicator.exchange": {
"total": 203.466014139006,
"count": 18199,
"is_parallel": true,
"self": 203.466014139006
},
"steps_from_proto": {
"total": 37.748478880000846,
"count": 18199,
"is_parallel": true,
"self": 7.096025810019398,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.652453069981448,
"count": 181990,
"is_parallel": true,
"self": 30.652453069981448
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012834200003908336,
"count": 1,
"self": 0.00012834200003908336,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 477.8015650810165,
"count": 439854,
"is_parallel": true,
"self": 10.223229598978037,
"children": {
"process_trajectory": {
"total": 262.80181743503874,
"count": 439854,
"is_parallel": true,
"self": 261.5925173750387,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2093000600000323,
"count": 4,
"is_parallel": true,
"self": 1.2093000600000323
}
}
},
"_update_policy": {
"total": 204.77651804699974,
"count": 90,
"is_parallel": true,
"self": 78.88821313200009,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.88830491499965,
"count": 4587,
"is_parallel": true,
"self": 125.88830491499965
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15999856199994156,
"count": 1,
"self": 0.000970920999975533,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15902764099996602,
"count": 1,
"self": 0.15902764099996602
}
}
}
}
}
}
}